Training in progress, step 2080, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51e8fa7e0cb43a50e7517c47741f3febcc6d4496dfaaa1fef564f0f83a397ab4
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d4dc1a62ed01d68696800b261752daae62095dcc2836cffbd7b1175f1250fe2
|
| 3 |
size 14709
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61581ab0b1028ba4097779bbbf155e0d48cbadcecc4e496b17938f15a6035055
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -3734,6 +3734,24 @@
|
|
| 3734 |
"mean_token_accuracy": 0.6618927121162415,
|
| 3735 |
"num_tokens": 7549141.0,
|
| 3736 |
"step": 2070
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3737 |
}
|
| 3738 |
],
|
| 3739 |
"logging_steps": 5,
|
|
@@ -3753,7 +3771,7 @@
|
|
| 3753 |
"attributes": {}
|
| 3754 |
}
|
| 3755 |
},
|
| 3756 |
-
"total_flos": 3.
|
| 3757 |
"train_batch_size": 4,
|
| 3758 |
"trial_name": null,
|
| 3759 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 16.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2080,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3734 |
"mean_token_accuracy": 0.6618927121162415,
|
| 3735 |
"num_tokens": 7549141.0,
|
| 3736 |
"step": 2070
|
| 3737 |
+
},
|
| 3738 |
+
{
|
| 3739 |
+
"epoch": 15.961538461538462,
|
| 3740 |
+
"grad_norm": 0.0,
|
| 3741 |
+
"learning_rate": 3.963e-05,
|
| 3742 |
+
"loss": 1.6903,
|
| 3743 |
+
"mean_token_accuracy": 0.6613986879587174,
|
| 3744 |
+
"num_tokens": 7567995.0,
|
| 3745 |
+
"step": 2075
|
| 3746 |
+
},
|
| 3747 |
+
{
|
| 3748 |
+
"epoch": 16.0,
|
| 3749 |
+
"grad_norm": 0.0,
|
| 3750 |
+
"learning_rate": 3.9605000000000005e-05,
|
| 3751 |
+
"loss": 1.7907,
|
| 3752 |
+
"mean_token_accuracy": 0.6406063586473465,
|
| 3753 |
+
"num_tokens": 7585680.0,
|
| 3754 |
+
"step": 2080
|
| 3755 |
}
|
| 3756 |
],
|
| 3757 |
"logging_steps": 5,
|
|
|
|
| 3771 |
"attributes": {}
|
| 3772 |
}
|
| 3773 |
},
|
| 3774 |
+
"total_flos": 3.8432667004452864e+17,
|
| 3775 |
"train_batch_size": 4,
|
| 3776 |
"trial_name": null,
|
| 3777 |
"trial_params": null
|